Update warnings (#1346)

* Added ignored_warnings file

* Use ignored_warnings file

* Test regressors with 1d, 1d as 2d and 2d targets

* Flake'd

* Fix broken relative imports to ignore_warnings

* Removed print and updated parameter type for tests

* Added warning catches to fit methods in tests

* Added more warning catches

* Flake'd

* Created top-level module to allow relativei imports

* Deleted blank line in __init__

* Remove uneeded ignore warnings from tests

* Fix bad indent

* Fix github merge conflict editor whitespaces and indents

test/test_automl/test_automl.py

@@ -64,9 +64,9 @@ def test_fit(dask_client):
         metric=accuracy,
         dask_client=dask_client,
     )
-    automl.fit(
-        X_train, Y_train, task=MULTICLASS_CLASSIFICATION
-    )
+
+    automl.fit(X_train, Y_train, task=MULTICLASS_CLASSIFICATION)
+
     score = automl.score(X_test, Y_test)
     assert score > 0.8
     assert count_succeses(automl.cv_results_) > 0
@@ -109,9 +109,9 @@ def get_roar_object_callback(
         metric=accuracy,
         dask_client=dask_client_single_worker,
     )
-    automl.fit(
-        X_train, Y_train, task=MULTICLASS_CLASSIFICATION,
-    )
+
+    automl.fit(X_train, Y_train, task=MULTICLASS_CLASSIFICATION)
+
     score = automl.score(X_test, Y_test)
     assert score > 0.8
     assert count_succeses(automl.cv_results_) > 0
@@ -224,8 +224,7 @@ def test_delete_non_candidate_models(dask_client):
         max_models_on_disc=3,
     )
 
-    automl.fit(X, Y, task=MULTICLASS_CLASSIFICATION,
-               X_test=X, y_test=Y)
+    automl.fit(X, Y, task=MULTICLASS_CLASSIFICATION, X_test=X, y_test=Y)
 
     # Assert at least one model file has been deleted and that there were no
     # deletion errors
@@ -271,7 +270,9 @@ def test_binary_score_and_include(dask_client):
         metric=accuracy,
         dask_client=dask_client,
     )
+
     automl.fit(X_train, Y_train, task=BINARY_CLASSIFICATION)
+
     assert automl._task == BINARY_CLASSIFICATION
 
     # TODO, the assumption from above is not really tested here
@@ -294,6 +295,7 @@ def test_automl_outputs(dask_client):
         dask_client=dask_client,
         delete_tmp_folder_after_terminate=False,
     )
+
     auto.fit(
         X=X_train,
         y=Y_train,
@@ -302,6 +304,7 @@ def test_automl_outputs(dask_client):
         dataset_name=name,
         task=MULTICLASS_CLASSIFICATION,
     )
+
     data_manager_file = os.path.join(
         auto._backend.temporary_directory,
         '.auto-sklearn',
@@ -624,9 +627,8 @@ def test_load_best_individual_model(metric, dask_client):
     # We cannot easily mock a function sent to dask
     # so for this test we create the whole set of models/ensembles
     # but prevent it to be loaded
-    automl.fit(
-        X_train, Y_train, task=MULTICLASS_CLASSIFICATION,
-    )
+    automl.fit(X_train, Y_train, task=MULTICLASS_CLASSIFICATION)
+
     automl._backend.load_ensemble = unittest.mock.MagicMock(return_value=None)
 
     # A memory error occurs in the ensemble construction

test/test_automl/test_estimators.py

@@ -79,6 +79,7 @@ def __call__(self, *args, **kwargs):
         get_smac_object_callback=get_smac_object_wrapper_instance,
         max_models_on_disc=None,
     )
+
     automl.fit(X_train, Y_train)
 
     # Test that the argument is correctly passed to SMAC
@@ -272,6 +273,7 @@ def test_performance_over_time_no_ensemble(tmp_dir):
                                 seed=1,
                                 initial_configurations_via_metalearning=0,
                                 ensemble_size=0,)
+
     cls.fit(X_train, Y_train, X_test, Y_test)
 
     performance_over_time = cls.performance_over_time_
@@ -297,6 +299,7 @@ def test_cv_results(tmp_dir):
     original_params = copy.deepcopy(params)
 
     cls.fit(X_train, Y_train)
+
     cv_results = cls.cv_results_
     assert isinstance(cv_results, dict), type(cv_results)
     assert isinstance(cv_results['mean_test_score'], np.ndarray), type(
@@ -382,6 +385,7 @@ def test_leaderboard(
         tmp_folder=tmp_dir,
         seed=1
     )
+
     model.fit(X_train, Y_train)
 
     for params in params_generator:
@@ -540,6 +544,7 @@ def test_can_pickle_classifier(tmp_dir, dask_client):
                                    tmp_folder=tmp_dir,
                                    dask_client=dask_client,
                                    )
+
     automl.fit(X_train, Y_train)
 
     initial_predictions = automl.predict(X_test)
@@ -765,12 +770,14 @@ def test_autosklearn_classification_methods_returns_self(dask_client):
                                    exclude={'feature_preprocessor': ['fast_ica']})
 
     automl_fitted = automl.fit(X_train, y_train)
+
     assert automl is automl_fitted
 
     automl_ensemble_fitted = automl.fit_ensemble(y_train, ensemble_size=5)
     assert automl is automl_ensemble_fitted
 
     automl_refitted = automl.refit(X_train.copy(), y_train.copy())
+
     assert automl is automl_refitted
 
 
@@ -801,12 +808,14 @@ def test_autosklearn2_classification_methods_returns_self(dask_client):
                                     dask_client=dask_client)
 
     automl_fitted = automl.fit(X_train, y_train)
+
     assert automl is automl_fitted
 
     automl_ensemble_fitted = automl.fit_ensemble(y_train, ensemble_size=5)
     assert automl is automl_ensemble_fitted
 
     automl_refitted = automl.refit(X_train.copy(), y_train.copy())
+
     assert automl is automl_refitted
 
     predictions = automl_fitted.predict(X_test)
@@ -824,12 +833,14 @@ def test_autosklearn2_classification_methods_returns_self_sparse(dask_client):
                                     dask_client=dask_client)
 
     automl_fitted = automl.fit(X_train, y_train)
+
     assert automl is automl_fitted
 
     automl_ensemble_fitted = automl.fit_ensemble(y_train, ensemble_size=5)
     assert automl is automl_ensemble_fitted
 
     automl_refitted = automl.refit(X_train.copy(), y_train.copy())
+
     assert automl is automl_refitted
 
     predictions = automl_fitted.predict(X_test)
@@ -933,10 +944,15 @@ def test_fit_pipeline(dask_client, task_type, resampling_strategy, disable_file_
                                             X_test=X_test, y_test=y_test,
                                             ).get_default_configuration()
 
-    pipeline, run_info, run_value = automl.fit_pipeline(X=X_train, y=y_train, config=config,
-                                                        X_test=X_test, y_test=y_test,
-                                                        disable_file_output=disable_file_output,
-                                                        resampling_strategy=resampling_strategy)
+    pipeline, run_info, run_value = automl.fit_pipeline(
+        X=X_train,
+        y=y_train,
+        config=config,
+        X_test=X_test,
+        y_test=y_test,
+        disable_file_output=disable_file_output,
+        resampling_strategy=resampling_strategy
+    )
 
     assert isinstance(run_info.config, Configuration)
     assert run_info.cutoff == 30
@@ -1090,11 +1106,14 @@ def test_autosklearn_anneal(as_frame):
     if as_frame:
         # Let autosklearn calculate the feat types
         automl_fitted = automl.fit(X, y)
+
     else:
         X_, y_ = sklearn.datasets.fetch_openml(data_id=2, return_X_y=True, as_frame=True)
         feat_type = ['categorical' if X_[col].dtype.name == 'category' else 'numerical'
                      for col in X_.columns]
+
         automl_fitted = automl.fit(X, y, feat_type=feat_type)
+
     assert automl is automl_fitted
 
     automl_ensemble_fitted = automl.fit_ensemble(y, ensemble_size=5)

test/test_pipeline/components/classification/test_base.py

@@ -9,6 +9,8 @@
 import sklearn.metrics
 import numpy as np
 
+from ...ignored_warnings import ignore_warnings, classifier_warnings
+
 
 class BaseClassificationComponentTest(unittest.TestCase):
     # Magic command to not run tests on base class
@@ -274,7 +276,8 @@ def is_unset_param_raw_predictions_val_error(err):
                         + " assignment" in err.args[0])
 
             try:
-                model.fit(X.copy(), y.copy())
+                with ignore_warnings(classifier_warnings):
+                    model.fit(X.copy(), y.copy())
             except ValueError as e:
                 if is_AdaBoostClassifier_error(e) or is_QDA_error(e):
                     return None

test/test_pipeline/components/feature_preprocessing/test_liblinear.py

@@ -5,10 +5,15 @@
     get_dataset
 import sklearn.metrics
 
+from ...ignored_warnings import ignore_warnings, feature_preprocessing_warnings
+
 
 class LiblinearComponentTest(PreprocessingTestCase):
+
     def test_default_configuration(self):
-        transformation, original = _test_preprocessing(LibLinear_Preprocessor)
+        with ignore_warnings(feature_preprocessing_warnings):
+            transformation, original = _test_preprocessing(LibLinear_Preprocessor)
+
         self.assertEqual(transformation.shape[0], original.shape[0])
         self.assertFalse((transformation == 0).all())
 
@@ -23,7 +28,10 @@ def test_default_configuration_classify(self):
                                                      for hp_name in
                                                      default if default[
                                                       hp_name] is not None})
-            preprocessor.fit(X_train, Y_train)
+
+            with ignore_warnings(feature_preprocessing_warnings):
+                preprocessor.fit(X_train, Y_train)
+
             X_train_trans = preprocessor.transform(X_train)
             X_test_trans = preprocessor.transform(X_test)
 
@@ -35,6 +43,6 @@ def test_default_configuration_classify(self):
             self.assertAlmostEqual(accuracy, 0.8548876745598057, places=2)
 
     def test_preprocessing_dtype(self):
-        super(LiblinearComponentTest,
-              self)._test_preprocessing_dtype(LibLinear_Preprocessor,
-                                              test_sparse=False)
+
+        with ignore_warnings(feature_preprocessing_warnings):
+            super()._test_preprocessing_dtype(LibLinear_Preprocessor, test_sparse=False)